© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25153
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    309
    +0.12
    0.7%
    38
    +0.11
    0.6%
    440
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.38
    434
    +0.11
    0.30
    151
    +0.11
    0.31
    Negative Logits
     reason
    -1.61
     lie
    -1.59
     truth
    -1.56
     doubt
    -1.55
     halluc
    -1.53
     question
    -1.51
    woke
    -1.50
     confession
    -1.46
     fact
    -1.45
     disagreement
    -1.42
    POSITIVE LOGITS
    olini
    2.06
    ulent
    1.89
    ovascular
    1.71
    ENTIAL
    1.70
    ridge
    1.63
    ľĵ
    1.62
    ĨĴ
    1.61
    rol
    1.57
    rolet
    1.55
    olis
    1.53
    Activations Density 1.654%

    No Known Activations